#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
+#include <linux/slab.h>
#include <asm/uaccess.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
solution, but it supposes maintaing new variable in ALL
skb, even if no tunneling is used.
- Current solution: t->recursion lock breaks dead loops. It looks
- like dev->tbusy flag, but I preferred new variable, because
- the semantics is different. One day, when hard_start_xmit
- will be multithreaded we will have to use skb->encapsulation.
+ Current solution: HARD_TX_LOCK lock breaks dead loops.
#define HASH_SIZE 16
-static int ipgre_net_id;
+static int ipgre_net_id __read_mostly;
struct ipgre_net {
struct ip_tunnel *tunnels[4][HASH_SIZE];
#define tunnels_r tunnels[2]
#define tunnels_l tunnels[1]
#define tunnels_wc tunnels[0]
+/*
+ * Locking : hash tables are protected by RCU and a spinlock
+ */
+static DEFINE_SPINLOCK(ipgre_lock);
-static DEFINE_RWLOCK(ipgre_lock);
+#define for_each_ip_tunnel_rcu(start) \
+ for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
/* Given src, dst and key, find appropriate for input tunnel. */
ARPHRD_ETHER : ARPHRD_IPGRE;
int score, cand_score = 4;
- for (t = ign->tunnels_r_l[h0^h1]; t; t = t->next) {
+ for_each_ip_tunnel_rcu(ign->tunnels_r_l[h0 ^ h1]) {
if (local != t->parms.iph.saddr ||
remote != t->parms.iph.daddr ||
key != t->parms.i_key ||
}
}
- for (t = ign->tunnels_r[h0^h1]; t; t = t->next) {
+ for_each_ip_tunnel_rcu(ign->tunnels_r[h0 ^ h1]) {
if (remote != t->parms.iph.daddr ||
key != t->parms.i_key ||
!(t->dev->flags & IFF_UP))
}
}
- for (t = ign->tunnels_l[h1]; t; t = t->next) {
+ for_each_ip_tunnel_rcu(ign->tunnels_l[h1]) {
if ((local != t->parms.iph.saddr &&
(local != t->parms.iph.daddr ||
!ipv4_is_multicast(local))) ||
}
}
- for (t = ign->tunnels_wc[h1]; t; t = t->next) {
+ for_each_ip_tunnel_rcu(ign->tunnels_wc[h1]) {
if (t->parms.i_key != key ||
!(t->dev->flags & IFF_UP))
continue;
if (cand != NULL)
return cand;
- if (ign->fb_tunnel_dev->flags & IFF_UP)
- return netdev_priv(ign->fb_tunnel_dev);
+ dev = ign->fb_tunnel_dev;
+ if (dev->flags & IFF_UP)
+ return netdev_priv(dev);
return NULL;
}
{
struct ip_tunnel **tp = ipgre_bucket(ign, t);
+ spin_lock_bh(&ipgre_lock);
t->next = *tp;
- write_lock_bh(&ipgre_lock);
- *tp = t;
- write_unlock_bh(&ipgre_lock);
+ rcu_assign_pointer(*tp, t);
+ spin_unlock_bh(&ipgre_lock);
}
static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t)
for (tp = ipgre_bucket(ign, t); *tp; tp = &(*tp)->next) {
if (t == *tp) {
- write_lock_bh(&ipgre_lock);
+ spin_lock_bh(&ipgre_lock);
*tp = t->next;
- write_unlock_bh(&ipgre_lock);
+ spin_unlock_bh(&ipgre_lock);
break;
}
}
break;
}
- read_lock(&ipgre_lock);
+ rcu_read_lock();
t = ipgre_tunnel_lookup(skb->dev, iph->daddr, iph->saddr,
flags & GRE_KEY ?
*(((__be32 *)p) + (grehlen / 4) - 1) : 0,
t->err_count = 1;
t->err_time = jiffies;
out:
- read_unlock(&ipgre_lock);
+ rcu_read_unlock();
return;
}
gre_proto = *(__be16 *)(h + 2);
- read_lock(&ipgre_lock);
+ rcu_read_lock();
if ((tunnel = ipgre_tunnel_lookup(skb->dev,
iph->saddr, iph->daddr, key,
gre_proto))) {
ipgre_ecn_decapsulate(iph, skb);
netif_rx(skb);
- read_unlock(&ipgre_lock);
+ rcu_read_unlock();
return(0);
}
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
drop:
- read_unlock(&ipgre_lock);
+ rcu_read_unlock();
drop_nolock:
kfree_skb(skb);
return(0);
}
-static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
- struct net_device_stats *stats = &tunnel->dev->stats;
+ struct net_device_stats *stats = &dev->stats;
+ struct netdev_queue *txq = netdev_get_tx_queue(dev, 0);
struct iphdr *old_iph = ip_hdr(skb);
struct iphdr *tiph;
u8 tos;
__be32 dst;
int mtu;
- if (tunnel->recursion++) {
- stats->collisions++;
- goto tx_error;
- }
-
if (dev->type == ARPHRD_ETHER)
IPCB(skb)->flags = 0;
}
if (mtu >= IPV6_MIN_MTU && mtu < skb->len - tunnel->hlen + gre_hlen) {
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
ip_rt_put(rt);
goto tx_error;
}
tunnel->err_count = 0;
}
- max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen;
+ max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + rt->u.dst.header_len;
if (skb_headroom(skb) < max_headroom || skb_shared(skb)||
(skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
+ if (max_headroom > dev->needed_headroom)
+ dev->needed_headroom = max_headroom;
if (!new_skb) {
ip_rt_put(rt);
- stats->tx_dropped++;
+ txq->tx_dropped++;
dev_kfree_skb(skb);
- tunnel->recursion--;
return NETDEV_TX_OK;
}
if (skb->sk)
nf_reset(skb);
IPTUNNEL_XMIT();
- tunnel->recursion--;
return NETDEV_TX_OK;
tx_error_icmp:
tx_error:
stats->tx_errors++;
dev_kfree_skb(skb);
- tunnel->recursion--;
return NETDEV_TX_OK;
}
addend += 4;
}
dev->needed_headroom = addend + hlen;
- mtu -= dev->hard_header_len - addend;
+ mtu -= dev->hard_header_len + addend;
if (mtu < 68)
mtu = 68;
if (saddr)
memcpy(&iph->saddr, saddr, 4);
-
- if (daddr) {
+ if (daddr)
memcpy(&iph->daddr, daddr, 4);
- return t->hlen;
- }
- if (iph->daddr && !ipv4_is_multicast(iph->daddr))
+ if (iph->daddr)
return t->hlen;
return -t->hlen;
}
-static struct net_protocol ipgre_protocol = {
+static const struct net_protocol ipgre_protocol = {
.handler = ipgre_rcv,
.err_handler = ipgre_err,
.netns_ok = 1,
};
-static void ipgre_destroy_tunnels(struct ipgre_net *ign)
+static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head)
{
int prio;
for (prio = 0; prio < 4; prio++) {
int h;
for (h = 0; h < HASH_SIZE; h++) {
- struct ip_tunnel *t;
- while ((t = ign->tunnels[prio][h]) != NULL)
- unregister_netdevice(t->dev);
+ struct ip_tunnel *t = ign->tunnels[prio][h];
+
+ while (t != NULL) {
+ unregister_netdevice_queue(t->dev, head);
+ t = t->next;
+ }
}
}
}
-static int ipgre_init_net(struct net *net)
+static int __net_init ipgre_init_net(struct net *net)
{
+ struct ipgre_net *ign = net_generic(net, ipgre_net_id);
int err;
- struct ipgre_net *ign;
-
- err = -ENOMEM;
- ign = kzalloc(sizeof(struct ipgre_net), GFP_KERNEL);
- if (ign == NULL)
- goto err_alloc;
-
- err = net_assign_generic(net, ipgre_net_id, ign);
- if (err < 0)
- goto err_assign;
ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "gre0",
ipgre_tunnel_setup);
err_reg_dev:
free_netdev(ign->fb_tunnel_dev);
err_alloc_dev:
- /* nothing */
-err_assign:
- kfree(ign);
-err_alloc:
return err;
}
-static void ipgre_exit_net(struct net *net)
+static void __net_exit ipgre_exit_net(struct net *net)
{
struct ipgre_net *ign;
+ LIST_HEAD(list);
ign = net_generic(net, ipgre_net_id);
rtnl_lock();
- ipgre_destroy_tunnels(ign);
+ ipgre_destroy_tunnels(ign, &list);
+ unregister_netdevice_many(&list);
rtnl_unlock();
- kfree(ign);
}
static struct pernet_operations ipgre_net_ops = {
.init = ipgre_init_net,
.exit = ipgre_exit_net,
+ .id = &ipgre_net_id,
+ .size = sizeof(struct ipgre_net),
};
static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[])
ether_setup(dev);
- dev->netdev_ops = &ipgre_netdev_ops;
+ dev->netdev_ops = &ipgre_tap_netdev_ops;
dev->destructor = free_netdev;
dev->iflink = 0;
dev->features |= NETIF_F_NETNS_LOCAL;
}
-static int ipgre_newlink(struct net_device *dev, struct nlattr *tb[],
+static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[])
{
struct ip_tunnel *nt;
if (t->dev != dev)
return -EEXIST;
} else {
- unsigned nflags = 0;
-
t = nt;
- if (ipv4_is_multicast(p.iph.daddr))
- nflags = IFF_BROADCAST;
- else if (p.iph.daddr)
- nflags = IFF_POINTOPOINT;
+ if (dev->type != ARPHRD_ETHER) {
+ unsigned nflags = 0;
- if ((dev->flags ^ nflags) &
- (IFF_POINTOPOINT | IFF_BROADCAST))
- return -EINVAL;
+ if (ipv4_is_multicast(p.iph.daddr))
+ nflags = IFF_BROADCAST;
+ else if (p.iph.daddr)
+ nflags = IFF_POINTOPOINT;
+
+ if ((dev->flags ^ nflags) &
+ (IFF_POINTOPOINT | IFF_BROADCAST))
+ return -EINVAL;
+ }
ipgre_tunnel_unlink(ign, t);
t->parms.iph.saddr = p.iph.saddr;
t->parms.iph.daddr = p.iph.daddr;
t->parms.i_key = p.i_key;
- memcpy(dev->dev_addr, &p.iph.saddr, 4);
- memcpy(dev->broadcast, &p.iph.daddr, 4);
+ if (dev->type != ARPHRD_ETHER) {
+ memcpy(dev->dev_addr, &p.iph.saddr, 4);
+ memcpy(dev->broadcast, &p.iph.daddr, 4);
+ }
ipgre_tunnel_link(ign, t);
netdev_state_change(dev);
}
printk(KERN_INFO "GRE over IPv4 tunneling driver\n");
- if (inet_add_protocol(&ipgre_protocol, IPPROTO_GRE) < 0) {
+ err = register_pernet_device(&ipgre_net_ops);
+ if (err < 0)
+ return err;
+
+ err = inet_add_protocol(&ipgre_protocol, IPPROTO_GRE);
+ if (err < 0) {
printk(KERN_INFO "ipgre init: can't add protocol\n");
- return -EAGAIN;
+ goto add_proto_failed;
}
- err = register_pernet_gen_device(&ipgre_net_id, &ipgre_net_ops);
- if (err < 0)
- goto gen_device_failed;
-
err = rtnl_link_register(&ipgre_link_ops);
if (err < 0)
goto rtnl_link_failed;
tap_ops_failed:
rtnl_link_unregister(&ipgre_link_ops);
rtnl_link_failed:
- unregister_pernet_gen_device(ipgre_net_id, &ipgre_net_ops);
-gen_device_failed:
inet_del_protocol(&ipgre_protocol, IPPROTO_GRE);
+add_proto_failed:
+ unregister_pernet_device(&ipgre_net_ops);
goto out;
}
{
rtnl_link_unregister(&ipgre_tap_ops);
rtnl_link_unregister(&ipgre_link_ops);
- unregister_pernet_gen_device(ipgre_net_id, &ipgre_net_ops);
if (inet_del_protocol(&ipgre_protocol, IPPROTO_GRE) < 0)
printk(KERN_INFO "ipgre close: can't remove protocol\n");
+ unregister_pernet_device(&ipgre_net_ops);
}
module_init(ipgre_init);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff